{
  "tokenizer_class": "DebertaV2Tokenizer",
  "model_input_names": [
    "input_ids",
    "attention_mask"
  ],
  "unk_token": "[UNK]",
  "pad_token": "[PAD]",
  "cls_token": "[CLS]",
  "sep_token": "[SEP]",
  "mask_token": "[MASK]",
  "do_lower_case": false,
  "keep_accents": true,
  "split_by_punct": false,
  "padding_side": "right",
  "truncation_side": "right",
  "model_max_length": 512,
  "latin_lowercase_before_encode": true,
  "note": "Lowercase Latin spans before encoding; the tokenizer then wraps input as [CLS] chunk [SEP]. See the model card."
}